Single image haze removal using variable fog-weight

Abstract

In this paper, a new Image Haze Removal technique is proposed using variable fog-weight. The objective of the proposed technique is to improve the visibility, to remove the impact of weather factors and make image more usable. To achieve this, it is required to estimate the transmission map as well as atmospheric light by using Dark Channel Prior. The main contribution in this work, is to vary the fog-weight during transmission estimation. It is varied according to the density of haze in the input image. If the density of the haze in the input image is low, then lower fog-weight value will be applied and if the haze density in the input image is higher, than higher fog-weight value will be applied, according to the haze concentration. A guided filter is used as a refiner of transmission map to avoid the halo artifacts at the boundary of the edge. It provides smoothness to the image and build-up the visibility of the image, so that we restore a superior haze free image. At last, the performance of the proposed method is compared with some of the existing methods in terms of visibility, computational time and avoidance of halo effect.